© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128987
    Prev
    Next
    INDEX
    Explanations

    costs and expenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heal
    -0.07
    otive
    -0.06
    ido
    -0.06
     heals
    -0.06
     وحدة
    -0.06
     영
    -0.06
    professional
    -0.06
    कम
    -0.06
     निशाना
    -0.06
    лева
    -0.06
    POSITIVE LOGITS
     expenses
    0.08
     expense
    0.08
    经费
    0.07
     هزینه
    0.07
     berat
    0.07
    費用
    0.07
     costs
    0.07
     biaya
    0.07
    成本
    0.07
     Expense
    0.07
    Activations Density 0.065%

    No Known Activations